© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17326
    Prev
    Next
    INDEX
    Explanations

    titles or headings within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "title" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratom
    -0.69
    gm
    -0.68
    istani
    -0.66
    ombo
    -0.66
     Spice
    -0.65
    ramid
    -0.64
    MQ
    -0.63
    addafi
    -0.63
    verages
    -0.63
    agan
    -0.62
    POSITIVE LOGITS
    plate
    0.94
    plates
    0.93
    holder
    0.88
    manship
    0.88
    card
    0.85
    holders
    0.83
    marks
    0.81
    boards
    0.80
     deeds
    0.80
    pad
    0.80
    Activations Density 0.036%

    No Known Activations